Search Results for author:
Found 38 papers, 12 papers with code
Data is Overrated: Perceptual Metrics Can Lead Learning in the Absence of Training Data
Perceptual metrics are traditionally used to evaluate the quality of natural signals, such as images and audio.
What You Hear Is What You See: Audio Quality Metrics From Image Quality Metrics
In this study, we investigate the feasibility of utilizing state-of-the-art image perceptual metrics for evaluating audio signals by representing them as spectrograms.
Disentangling the Link Between Image Statistics and Human Perception
Moreover, the direct evaluation of the hypothesis was limited by the inability of the classical image models to deliver accurate estimates of the probability.
Analysis of Deep Image Quality Models
In this work, we perform a thorough analysis of the perceptual properties of pre-trained nets (particularly their ability to predict image quality) by isolating different factors: the goal (the function), the data (learning environment), the architecture, and the readout: selected layer(s), fine-tuning of channel relevance, and use of statistical descriptors as opposed to plain readout of responses.
Orthonormal Convolutions for the Rotation Based Iterative Gaussianization
Here we present the \emph{Convolutional RBIG}: an extension that alleviates this issue by imposing that the rotation in RBIG is a convolution.
Unsupervised Anomaly and Change Detection with Multivariate Gaussianization
Identifying low probability events in data/images is a challenging problem given the high-dimensionality of the data, especially when no (or little) information about the anomaly is available a priori.
Inference over radiative transfer models using variational and expectation maximization methods
Radiative transfer models (RTMs) encode the energy transfer through the atmosphere, and are used to model and understand the Earth system, as well as to estimate the parameters that describe the status of the Earth from satellite observations by inverse modeling.
Neural Networks with Divisive normalization for image segmentation with application in cityscapes dataset
In addition to the results on the Cityscapes and Foggy Cityscapes datasets, we explain these advantages through visualization of the responses: the equalization induced by the divisive normalization leads to more invariant features to local changes in contrast and illumination.
On the relation between statistical learning and perceptual distances
Since machine learning relies on the statistics of training data as well, the above connection has interesting implications when using perceptual distances (which mimic the behavior of the human visual system) as a loss function.
Learning Structures in Earth Observation Data with Gaussian Processes
Gaussian Processes (GPs) has experienced tremendous success in geoscience in general and for bio-geophysical parameter retrieval in the last years.
Spatial noise-aware temperature retrieval from infrared sounder data
We compare Principal Component Analysis (PCA) and Minimum Noise Fraction (MNF) for dimensionality reduction, and study the compactness and information content of the extracted features.
Transfer Learning with Convolutional Networks for Atmospheric Parameter Retrieval
The Infrared Atmospheric Sounding Interferometer (IASI) on board the MetOp satellite series provides important measurements for Numerical Weather Prediction (NWP).
Kernel Anomalous Change Detection for Remote Sensing Imagery
Anomalous change detection (ACD) is an important problem in remote sensing image processing.
Disentangling Derivatives, Uncertainty and Error in Gaussian Process Models
Gaussian Processes (GPs) are a class of kernel methods that have shown to be very useful in geoscience applications.
Consistent regression of biophysical parameters with kernel methods
This paper introduces a novel statistical regression framework that allows the incorporation of consistency constraints.
Randomized kernels for large scale Earth observation applications
Dealing with land cover classification of the new image sources has also turned to be a complex problem requiring large amount of memory and processing time.
Physics-Aware Gaussian Processes in Remote Sensing
However, GPs are typically used for inverse modeling based on concurrent observations and in situ measurements only.
Information Theory in Density Destructors
Density destructors are differentiable and invertible transforms that map multivariate PDFs of arbitrary structure (low entropy) into non-structured PDFs (maximum entropy).
Gaussianizing the Earth: Multidimensional Information Measures for Earth Data Analysis
Information theory is an excellent framework for analyzing Earth system data because it allows us to characterize uncertainty and redundancy, and is universally interpretable.
Information Theory Measures via Multidimensional Gaussianization
Information theory is an outstanding framework to measure uncertainty, dependence and relevance in data and systems.
Kernel Methods and their derivatives: Concept and perspectives for the Earth system sciences
We note that model function derivatives in kernel machines is proportional to the kernel function derivative.
Cross-Sensor Adversarial Domain Adaptation of Landsat-8 and Proba-V images for Cloud Detection
In addition, the training of the proposed adversarial domain adaptation model can be modified to improve the performance in a specific remote sensing application, such as cloud detection, by including a dedicated term in the cost function.
Accounting for Input Noise in Gaussian Process Parameter Retrieval
In this letter, we demonstrate how one can account for input noise estimates using a GP model formulation which propagates the error terms using the derivative of the predictive mean function.
PerceptNet: A Human Visual System Inspired Neural Network for Estimating Perceptual Distance
Traditionally, the vision community has devised algorithms to estimate the distance between an original image and images that have been subject to perturbations.
Enforcing Perceptual Consistency on Generative Adversarial Networks by Using the Normalised Laplacian Pyramid Distance
While an important part of the evaluation of the generated images usually involves visual inspection, the inclusion of human perception as a factor in the training process is often overlooked.
Fair Kernel Learning
It has been shown that not including sensitive features that bias fairness, such as gender or race, is not enough to mitigate the discrimination when other related features are included.
Eigen-Distortions of Hierarchical Representations
We develop a method for comparing hierarchical image representations in terms of their ability to explain perceptual sensitivity in humans.
Perceptually Optimized Image Rendering
We develop a framework for rendering photographic images, taking into account display limitations, so as to optimize perceptual similarity between the rendered image and the original scene.
End-to-end Optimized Image Compression
We describe an image compression method, consisting of a nonlinear analysis transformation, a uniform quantizer, and a nonlinear synthesis transformation.
End-to-end optimization of nonlinear transform codes for perceptual quality
We introduce a general framework for end-to-end optimization of the rate--distortion performance of nonlinear transform codes assuming scalar quantization.
Sequential Principal Curves Analysis
The identified curvilinear features can be interpreted as a set of nonlinear sensors: the response of each sensor is the projection onto the corresponding feature.
Optimized Kernel Entropy Components
Results show that 1) OKECA returns projections with more expressive power than KECA, 2) the most successful rule for estimating the kernel parameter is based on maximum likelihood, and 3) OKECA is more robust to the selection of the length-scale parameter in kernel density estimation.
Nonlinearities and Adaptation of Color Vision from Sequential Principal Curves Analysis
Here we address the simultaneous statistical explanation of (i) the nonlinear behavior of achromatic and chromatic mechanisms in a fixed adaptation state, and (ii) the change of such behavior.
Dimensionality Reduction via Regression in Hyperspectral Imagery
DRR identifies the nonlinear features through multivariate regression to ensure the reduction in redundancy between he PCA coefficients, the reduction of the variance of the scores, and the reduction in the reconstruction error.
Iterative Gaussianization: from ICA to Random Rotations
The practical performance of RBIG is successfully illustrated in a number of multidimensional problems such as image synthesis, classification, denoising, and multi-information estimation.
Image Denoising with Kernels based on Natural Image Relations
In this paper, we propose an alternative non-explicit way to take into account the relations among natural image wavelet coefficients for denoising: we use support vector regression (SVR) in the wavelet domain to enforce these relations in the estimated signal.
Density Modeling of Images using a Generalized Normalization Transformation
The data are linearly transformed, and each component is then normalized by a pooled activity measure, computed by exponentiating a weighted sum of rectified and exponentiated components and a constant.
